Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    side hustles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    node
    0.50
    ="
    0.50
     was
    0.49
     on
    0.47
    S
    0.46
     at
    0.45
     a
    0.43
    L
    0.43
    })$
    0.42
    not
    0.41
    POSITIVE LOGITS
    大赛
    0.46
     recrut
    0.45
     referrals
    0.45
     outings
    0.44
     affaires
    0.43
     expériences
    0.43
     endorsements
    0.42
     соревнования
    0.42
     quotas
    0.41
    ओं
    0.41
    Act Density 0.001%

    No Known Activations